all AI news
Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality
March 15, 2024, 4:43 a.m. | Joshua Cutler, Mateo D\'iaz, Dmitriy Drusvyatskiy
cs.LG updates on arXiv.org arxiv.org
Abstract: We analyze a stochastic approximation algorithm for decision-dependent problems, wherein the data distribution used by the algorithm evolves along the iterate sequence. The primary examples of such problems appear in performative prediction and its multiplayer extensions. We show that under mild assumptions, the deviation between the average iterate of the algorithm and the solution is asymptotically normal, with a covariance that clearly decouples the effects of the gradient noise and the distributional shift. Moreover, building …
abstract algorithm analyze approximation arxiv assumptions cs.lg data decision deviation distribution examples extensions iterate math.oc multiplayer normality prediction show stat.ml stochastic the algorithm type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Machine Learning Engineer - Sr. Consultant level
@ Visa | Bellevue, WA, United States